分布式爬虫scrapy-redis源码超级详解

这几天完成了分布式爬虫的学习，发现了解scrapy-redis源代码对于分布式爬虫的学习真的很重要，废话少说，直接上干货：

1.创建项目

首先，我们要创建一个Scrapy项目来进行学习。创建项目用下面的代码在Terminal中执行。

scrapy startproject 项目名称

如图：

然后我们需要将scrapy-redis的源码拷贝到scrapy中，源码下载地址如下：
https://github.com/rmax/scrapy-redis
我们可以通过下载zip文件和git clone两种方式进行下载，个人建议还是用常见的下载zip文件比较方便。

2.源代码解析

分布式爬虫系统的结构如下：

scrapy-redis的源码中主要有以下几个文件：

connection.py
defaults.py
dupefilter.py
picklecompat.py
pipeline.py
queue.py
scheduler.py
spiders.py
utils.py

2.1 Connection.py

这个文件是用来连接redis的文件，与其他文件相比较而言，这个文件用到的次数是很多的，也是最重要的文件，Connection提供了一个非常重要的参数。pipeline，queue，scheduler文件都会调用。Connection.py文件解析如下：

import six
from scrapy.utils.misc import load_object

from . import defaults

# Shortcut maps 'setting name' -> 'parmater name'.
# redis数据库的关系映射
SETTINGS_PARAMS_MAP = {
   
    'REDIS_URL': 'url',
    'REDIS_HOST': 'host',
    'REDIS_PORT': 'port',
    'REDIS_ENCODING': 'encoding',
}


def get_redis_from_settings(settings):
    # 获取一个redis连接实例
    # 生成连接redis参数
    """Returns a redis client instance from given Scrapy settings object.

    This function uses ``get_client`` to instantiate the client and uses
    ``defaults.REDIS_PARAMS`` global as defaults values for the parameters. You
    can override them using the ``REDIS_PARAMS`` setting.

    Parameters
    ----------
    settings : Settings
        A scrapy settings object. See the supported settings below.

    Returns
    -------
    server
        Redis client instance.

    Other Parameters
    ----------------
    REDIS_URL : str, optional
        Server connection URL.
    REDIS_HOST : str, optional
        Server host.
    REDIS_PORT : str, optional
        Server port.
    REDIS_ENCODING : str, optional
        Data encoding.
    REDIS_PARAMS : dict, optional
        Additional client parameters.

    """
    # 浅拷贝，是为了防止params改变，会导致默认的REDIS_PARAMS被改变
    params = defaults.REDIS_PARAMS.copy()
    # 将settings中的参数更新到params
    params.update(settings.getdict('REDIS_PARAMS'))
    # XXX: Deprecate REDIS_* settings.
    # 遍历映射表，获取指定的参数
    for source, dest in SETTINGS_PARAMS_MAP.items():
        # 优先使用settings中的参数
        val = settings.get(source)
        # 如果settings中没有进行设置，则params不更新
        if val:
            params[dest] = val

    # Allow ``redis_cls`` to be a path to a class.
    if isinstance(params.get('redis_cls'), six.string_types):
        params['redis_cls'] = load_object(params['redis_cls'])

    return get_redis(**params)


# Backwards compatible alias.
from_settings = get_redis_from_settings


def get_redis(**kwargs):
    """Returns a redis client instance.

    Parameters
    ----------
    redis_cls : class, optional
        Defaults to ``redis.StrictRedis``.
    url : str, optional
        If given, ``redis_cls.from_url`` is used to instantiate the class.
    **kwargs
        Extra parameters to be passed to the ``redis_cls`` class.

    Returns
    -------
    server
        Redis client instance.

    """
    # 没有redis_cli，则默认redis连接
    redis_cls = kwargs.pop('redis_cls', defaults.REDIS_CLS)
    url = kwargs.pop('url', None) # 判断kwargs有没有url
    if url:
        #用url链接redis，优先使用url连接redis
        return redis_cls.from_url(url, **kwargs)
    else:
        #用字典的方式连接redis
        return redis_cls(**kwargs)

2.2 defaults.py

import redis


# For standalone use.
# 去重的键名
DUPEFILTER_KEY = 'dupefilter:%(timestamp)s'
# 定义的存储items的键名（key），spider是爬虫的名称
PIPELINE_KEY = '%(spider)s:items'
# Redis的连接对象，用于连接redis
REDIS_CLS = redis.StrictRedis
# 字符集编码
REDIS_ENCODING = 'utf-8'
# Sane connection defaults.
# redis数据库的连接参数
REDIS_PARAMS = {
   
    'socket_timeout': 30,
    'socket_connect_timeout': 30,
    'retry_on_timeout': True,
    'encoding': REDIS_ENCODING,
}
# 队列的变量名，用于存储爬取的url队列
SCHEDULER_QUEUE_KEY = '%(spider)s:requests'
# 优先级队列，用于规定队列的进出方式
SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.PriorityQueue'
# 用于去重的key值，给request加指纹存储的地方
SCHEDULER_DUPEFILTER_KEY = '%(spider)s:dupefilter'
# 用于生成指纹的类
SCHEDULER_DUPEFILTER_CLASS = 'scrapy_redis.dupefilter.RFPDupeFilter'
#起始url对应的类（key）
START_URLS_KEY = '%(name)s:start_urls'
#起始url的类型
START_URLS_AS_SET = False

2.3 dupefilter.py

import logging
import time

from scrapy.dupefilters import BaseDupeFilter
from scrapy.utils.request import request_fingerprint

from . import defaults
from .connection import get_redis_from_settings

logger = logging.getLogger(__name__)

# scrapy去重是利用集合实现的
# TODO: Rename class to RedisDupeFilter.
class RFPDupeFilter(BaseDupeFilter):
    """Redis-based request duplicates filter.

    This class can also be used with default Scrapy's scheduler.

    """

    logger = logger

    def __init__(self, server, key, debug=False):
        """Initialize the duplicates filter.

        Parameters
        ----------
        server : redis.StrictRedis
            The redis server instance.
            redis 连接实例

        key : str  存储requests指纹的地方
            Redis key Where to store fingerprints.
        debug : bool, optional
            Whether to log filtered requests.
            是否记录过滤的requests

        """
        #看server是如何生成的，因为我们通过server就可以获取redis中的队列或者set
        self.server = server
        self.key = key
        self.debug = debug
        self.logdupes = True
    # 类方法传递当前的方法
    @classmethod
    def from_settings(cls, settings):
        """Returns an instance from given settings.

        This uses by default the key ``dupefilter:<timestamp>``. When using the
        ``scrapy_redis.scheduler.Scheduler`` class, this method is not used as
        it needs to pass the spider name in the key.

        Parameters
        ----------
        settings : scrapy.settings.Settings

        Returns
        -------
        RFPDupeFilter
            A RFPDupeFilter instance.


        """
        # 获取redis的连接实例
        server = get_redis_from_settings(settings)
        # XXX: This creates one-time key. needed to support to use this
        # class as standalone dupefilter with scrapy's default scheduler
        # if scrapy passes spider on open() method this wouldn't be needed
        # TODO: Use SCRAPY_JOB env as default and fallback to timestamp.
        # 存取指纹的key
        key = defaults.DUPEFILTER_KEY % {
   'timestamp': int(time.time())}
        debug = settings.getbool('DUPEFILTER_DEBUG') # 默认值是false
        # 传给当前类，并把参数传递给init函数
        return cls(server, key=key, debug=debug)

    @classmethod
    def from_crawler(cls, crawler):
        """Returns instance from crawler.

        Parameters
        ----------
        crawler : scrapy.crawler.Crawler

        Returns
        -------
        RFPDupeFilter
            Instance of RFPDupeFilter.

        """
        return cls.from_settings(crawler.settings)

    def request_seen(self, request):
        """Returns True if request was already seen.

        Parameters
        ----------
        request : scrapy.http.Request

        Returns
        -------
        bool

        """
        fp = self.request_fingerprint(request) # 生成一个指纹
        # This returns the number of values added, zero if already exists.
        # 将 指纹加入redis  是一个集合类型
        # self.server redis连接实例
        # self.key 存储指纹的key
        # fp  就是指纹
        added = self.server.sadd(self.key, fp)
        # 当added为0，说明指纹已经存在，返回True，否则返回False
        return added == 0

    def request_fingerprint(self, request):
        """Returns a fingerprint for a given req